Empirical Evaluation of PDF Parsing and Chunking for Financial Question Answering with RAG

• URL: http://arxiv.org/abs/2604.12047v1
• Date: Mon, 13 Apr 2026 20:39:43 GMT
• Title: Empirical Evaluation of PDF Parsing and Chunking for Financial Question Answering with RAG
• Abstract summary: We study how different components and design choices affect the performance of a RAG system for understanding PDFs.<n>We systematically examine multiple PDF pipelines for chunking strategies.<n>Our results offer practical guidelines for building robust RAG PDF understanding.
• Score: 11.902442699404403
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: PDF files are primarily intended for human reading rather than automated processing. In addition, the heterogeneous content of PDFs, such as text, tables, and images, poses significant challenges for parsing and information extraction. To address these difficulties, both practitioners and researchers are increasingly developing new methods, including the promising Retrieval-Augmented Generation (RAG) systems to automated PDF processing. However, there is no comprehensive study investigating how different components and design choices affect the performance of a RAG system for understanding PDFs. In this paper, we propose such a study (1) by focusing on Question Answering, a specific language understanding task, and (2) by leveraging two benchmarks from the financial domain, including TableQuest, our newly generated, publicly available benchmark. We systematically examine multiple PDF parsers and chunking strategies (with varied overlap), along with their potential synergies in preserving document structure and ensuring answer correctness. Overall, our results offer practical guidelines for building robust RAG pipelines for PDF understanding.

Related papers

• Unlocking Biological Workflows for Robust Protein-Text Question Answering: A Dual-Dimensional RAG Framework [60.82334952881798]
  Protein-Text Question Answering (QA) is crucial for interpreting biological sequences through natural language.<n>We propose 2D-ProteinRAG, a novel framework that empowers Large Language Models (LLMs) to operate within the gold-standard biological research workflow.<n>We show that 2D-Protein consistently achieves state-of-the-art performance, outperforming fine-tuned baselines and other RAG methods.
  arXiv  Detail & Related papers  (2026-05-17T05:03:24Z)
• DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding [63.257540233507626]
  We propose a paradigm that requires the model to execute a structured textbfAnalysis, textbfLocalization and textbfReasoning'' workflow.<n>We show that DocSeeker achieves superior performance on both in-domain and out-of-domain tasks.
  arXiv  Detail & Related papers  (2026-04-14T14:39:26Z)
• From PDF to RAG-Ready: Evaluating Document Conversion Frameworks for Domain-Specific Question Answering [32.10503220086596]
  Retrieval-Augmented Generation (RAG) systems depend critically on the quality of document preprocessing.<n>No prior study has evaluated PDF processing frameworks by their impact on downstream question-answering accuracy.<n>We compare four open-source PDF-to-Markdown conversion frameworks, Docling, MinerU, Marker, and DeepSeek OCR, across 19 pipeline configurations.
  arXiv  Detail & Related papers  (2026-03-30T14:40:58Z)
• pdfQA: Diverse, Challenging, and Realistic Question Answering over PDFs [14.395485027306739]
  We present pdfQA, a multi-domain 2K human-annotated (real-pdfQA) and 2K synthetic dataset (syn-pdfQA)<n>We apply and evaluate quality and difficulty filters on both datasets, obtaining valid and challenging QA pairs.
  arXiv  Detail & Related papers  (2026-01-05T17:15:26Z)
• Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding [61.36285696607487]
  Document understanding is critical for applications from financial analysis to scientific discovery.<n>Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs) face key limitations.<n>Retrieval-Augmented Generation (RAG) helps ground models in external data, but documents' multimodal nature, combining text, tables, charts, and layout, demands a more advanced paradigm: Multimodal RAG.
  arXiv  Detail & Related papers  (2025-10-17T02:33:16Z)
• A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System [56.40989626804489]
  This survey provides the first holistic analysis of Large Language Models-powered software engineering.<n>We review over 150 recent papers and propose a taxonomy along two key dimensions: (1) Solutions, categorized into prompt-based, fine-tuning-based, and agent-based paradigms, and (2) Benchmarks, including tasks such as code generation, translation, and repair.
  arXiv  Detail & Related papers  (2025-10-10T06:56:50Z)
• DocR1: Evidence Page-Guided GRPO for Multi-Page Document Understanding [100.29587871213624]
  We introduce DocR1, an MLLM trained with a novel RL framework, Evidence Page-Guided GRPO.<n>EviGRPO incorporates an evidence-aware reward mechanism that promotes a coarse-to-fine reasoning strategy.<n>We show that DocR1 achieves state-of-the-art performance on multi-page tasks, while consistently maintaining strong results on single-page benchmarks.
  arXiv  Detail & Related papers  (2025-08-10T12:03:45Z)
• MMESGBench: Pioneering Multimodal Understanding and Complex Reasoning Benchmark for ESG Tasks [56.350173737493215]
  Environmental, Social, and Governance (ESG) reports are essential for evaluating sustainability practices, ensuring regulatory compliance, and promoting financial transparency.<n>MMESGBench is a first-of-its-kind benchmark dataset to evaluate multimodal understanding and complex reasoning across structurally diverse and multi-source ESG documents.<n>MMESGBench comprises 933 validated QA pairs derived from 45 ESG documents, spanning across seven distinct document types and three major ESG source categories.
  arXiv  Detail & Related papers  (2025-07-25T03:58:07Z)
• PDF Retrieval Augmented Question Answering [14.617711623828248]
  This paper presents an advancement in Question-Answering (QA) systems using a Retrieval Augmented Generation (RAG) framework.<n>We seek to develop a comprehensive RAG-based QA system that will effectively address complex multimodal questions.
  arXiv  Detail & Related papers  (2025-06-22T13:14:19Z)
• NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering [20.44642427268575]
  NeuSym-RAG is a hybrid neural symbolic retrieval framework which combines both paradigms in an interactive process.<n>NeuSym-RAG organizes semi-structured PDF content into both the relational database and vectorstore.<n> Experiments on three full PDF-based QA datasets, including a self-annotated one AIRQA-REAL, show that NeuSym-RAG stably defeats both the vector-based RAG and various structured baselines.
  arXiv  Detail & Related papers  (2025-05-26T09:33:10Z)
• Revolutionizing Retrieval-Augmented Generation with Enhanced PDF Structure Recognition [0.0]
  Major foundation model companies have opened up Embedding and Chat API interfaces, and frameworks like LangChain have already integrated the RAG process. This article discovers that current primary methods depend on the premise of accessing high-quality text corpora. We show that ChatDOC, a RAG system equipped with a panoptic and pinpoint PDF, retrieves more accurate and complete segments, and thus better answers.
  arXiv  Detail & Related papers  (2024-01-23T09:54:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.